prompt-optimizer

An agent skill by daymade, from daymade/claude-code-skills. Tags: analysis, documentation, generative, prompting, validation.

What it does

Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology. This skill should be used when users provide loose requirements, ambiguous feature descriptions, or need to enhance prompts for AI-generated code, products, or documents. Triggers include requests to "optimize my prompt", "improve this requirement", "make this more specific", or when raw requirements lack detail and structure.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill prompt-optimizer

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/prompt-optimizer ~/.claude/skills/prompt-optimizer

Safety box score

Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-13. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a documentation-only prompt/spec refinement skill. It reads bundled markdown references and outputs EARS-based structured prompts, so the main risk is downstream over-specification of sensitive workflows (e.g., auth, checkout), not direct machine access or side effects.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No scripts, shell commands, or code-evaluation paths are shipped; the files are plain markdown guidance and examples.
Network access	0 (none)	There is no instruction to fetch remote content or send data off-machine; the only external URLs are citations in prose.
Filesystem reach	0 (none)	The skill only refers to its own bundled reference markdown via "Load these reference files as needed" and does not edit or delete files.
Secrets & credentials	0 (none)	The files do not request passwords, tokens, .env files, keychains, or other credentials.
Privilege & persistence	0 (none)	No sudo, global installs, services, shell startup edits, or OS-level settings are mentioned.
Instruction hijack surface	0 (none)	There is no text telling the agent to ignore higher-priority instructions, hide content, or follow remote instructions.
Irreversible actions	0 (none)	The skill only transforms prompts; it does not itself publish, send messages, pay, book, deploy, or delete anything.
Transparency	0 (none)	All shipped files are human-readable markdown; there are no binaries, minified blobs, or decoded-at-runtime code.

Before installing

Read `SKILL.md` to confirm it only rewrites prompts/specs and has no side effects.
Skim `references/*.md` for whether you want its default examples to include sensitive domains like payments or authentication.
Run one harmless test prompt in a scratch chat and verify the output stays text-only and local.

Rated 2026-10-13 by an automated review of 5 files from the skill's repository.

Source

Repository: daymade/claude-code-skills (all skills from this repository)
Path: prompt-optimizer/SKILL.md
Branch: main
Updated: 2026-09-20

seo-content — Content quality and E-E-A-T analysis with AI citation readiness assessment.
verify-this — Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED.
deep-research — Generate format-controlled research reports with evidence tracking, citations, source governance, and multi-pass synthesis.
transcript-fixer — Corrects speech-to-text transcription errors with dictionary rules and Claude's built-in AI (no external API key required).
arena — Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
audit-prep-assistant — Prepares codebases for security review using Trail of Bits' checklist.